Research Plugins skill
A library of 400+ academic skills: literature search, reviews, statistics, scientific writing and grant proposals
- 310 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The OpenClaw plugin tools send search queries to 18 external academic databases
- Skills that include code (Python, Stata, LaTeX) can lead the agent to run it on your data
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/research-pluginsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The OpenClaw plugin tools send search queries to 18 external academic databases
- Skills that include code (Python, Stata, LaTeX) can lead the agent to run it on your data
This is third-party code. Review the repository files before installing.
What it does
Research Plugins is a library of skills for academic work from Wentor AI. It holds more than 400 SKILL.md files in six sections: literature, research methods, data analysis, academic writing, subject domains and utility tools. Topics include PRISMA systematic reviews, causal inference, LaTeX, replies to reviewers and grant proposals, NSF among them. Skills load in layers: the agent sees the six sections, then the subsections and only then the skill it needs, so the whole set never lands in context. The OpenClaw plugin adds 34 TypeScript tools. They query 18 open academic databases, including OpenAlex, CrossRef, PubMed, arXiv and Unpaywall, search for papers, resolve DOIs, collect citations and find free versions of articles.
Who it is for. Graduate students, researchers and academic editors who run literature search, data analysis and manuscript preparation together with an agent.
Good fit when
- A systematic review where the agent has to build a search string, a PRISMA flow and a screening protocol
- Panel data, a fixed-effects regression and robustness checks for it
- Reviewers sent three comments and you need a draft reply to each
- A grant proposal that needs a section outline and a budget based on the NSF guide
- A LaTeX paper whose references and formatting need cleaning up
Not a fit when
- The agent has to search databases directly from Claude Code: the catalog has Scholar Search MCP for that
- Subscription databases such as Scopus and Web of Science: the tools connect only to free open sources
- Everyday development or business writing: the skill sets are about research work
Example request
Build a search string and a PRISMA flow for a systematic review of causal inference in education economicsLimitations
The database tools are written as an OpenClaw plugin and do not run outside it. The plugin cannot be loaded from `node_modules` through pnpm: the OpenClaw security check rejects that path with `unsafe plugin manifest path`, so install it with `openclaw plugins install`. Some skills are compiled from open methodologies and API documentation, so method advice is worth checking against the primary source. The last commit in the repository dates from June 2026.
How to disable. In OpenClaw delete the plugin folder: `rm -rf ~/.openclaw/extensions/research-plugins`. For skills added with `npx skills add`, delete `.skills/wentorai/research-plugins`.
FAQ
How does installing with npx skills add differ from the OpenClaw plugin?
`npx skills add` installs only the SKILL.md files, which work in Claude Code, Cursor, Windsurf and OpenCode. The OpenClaw plugin adds 34 tools for querying academic databases; restart the gateway after installing.
Do the academic databases need API keys?
No. All 34 tools use free APIs, so no keys or paid subscriptions are required.
How can I tell where a particular skill came from?
If the content is based on a third-party open project, the SKILL.md frontmatter has a `source` field with the original link.
What is in the curated folder?
Six hand-picked resource lists, one per skill category. They are links to third-party projects and contain no code.
Which subject areas does the domains section cover?
Sixteen disciplines, including AI and machine learning, biomedicine, economics, law, chemistry and physics. It holds more skills than any other section.
Discussion
No questions or reviews yet.
Related
SkillsA Claude Code skill for scientific literature reviews: an interview, Scopus and OpenAlex search, DOI checks and a final docx file
A marketplace of five Claude Code plugins for researchers: literature search, research design, project memory and manuscript work
Research Skills
research-skills
Skills for scientific work: literature reviews on AI in medical imaging, a manuscript audit, slides. No paywall bypass, data comes from OpenAlex and PubMed
Skill with 30 prompt templates for research papers in English and Chinese, from literature review to grant proposals
An installable skill that gives an agent the full official OpenClaw documentation with progressive disclosure and a daily-synced snapshot
A skill for writing and revising ML, CV and NLP papers: section structure, paragraph flow and reviewer-style self-review
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| Research Plugins (this card) | no | 310 | ||
| Academic Skills for Claude Code & Codex | no | 5,698 | three skills for paper writing, Word and PowerPoint documents and scientific calculations; this one is a library of hundreds of skills with a set of API tools | |
| Scholar Search MCP | no | not required | 242 | an MCP server for paper search; this one offers skills and an OpenClaw plugin with database tools |
README in short
The README is in Chinese with an English version alongside. It explains what a general model lacks for academic work, gives six example requests with the chain of skills and tools behind each, then describes installation, the category table and the list of 34 tools. It closes with the repository layout, a section on where the material comes from and the MIT license.
README badge
Original SKILL.md
---
name: systematic-search-strategy
description: "Construct rigorous systematic search strategies for literature reviews"
metadata:
openclaw:
emoji: "🎯"
category: "literature"
subcategory: "search"
keywords: ["search strategy", "Boolean search", "search string construction", "advanced search", "systematic review"]
source: "wentor"
---
# Systematic Search Strategy
A skill for designing and executing comprehensive, reproducible literature search strategies for systematic reviews, scoping reviews, and meta-analyses. Follows PRISMA 2020 guidelines and Cochrane Handbook best practices.
## PICO Framework for Search Design
Structure your research question using PICO (or variants):
```
P - Population / Problem: Who or what is being studied?
I - Intervention / Exposure: What is the treatment or exposure?
C - Comparison: What is the alternative?
O - Outcome: What is being measured?
Variants:
PICOS: adds Study design
SPIDER: Sample, Phenomenon of Interest, Design, Evaluation, Research type
PCC: Population, Concept, Context (for scoping reviews)
```
### From PICO to Search Strategy
```python
def pico_to_search_blocks(pico: dict) -> dict:
"""
Convert a PICO question into search concept blocks.
Args:
pico: Dict with keys 'population', 'intervention', 'comparison', 'outcome'
Each value is a list of synonyms/related terms
Returns:
Search blocks ready for Boolean combination
"""